microsoft / RLHF-APALinks
RL algorithm: Advantage induced policy alignment
☆65Updated last year
Alternatives and similar repositories for RLHF-APA
Users that are interested in RLHF-APA are comparing it to the libraries listed below
Sorting:
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆43Updated last year
- ☆97Updated 11 months ago
- [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…☆51Updated last year
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆30Updated 11 months ago
- Directional Preference Alignment☆56Updated 8 months ago
- Reproduction of "RLCD Reinforcement Learning from Contrast Distillation for Language Model Alignment☆69Updated last year
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 8 months ago
- ☆93Updated 11 months ago
- Advantage Leftover Lunch Reinforcement Learning (A-LoL RL): Improving Language Models with Advantage-based Offline Policy Gradients☆26Updated 8 months ago
- Code for ACL2024 paper - Adversarial Preference Optimization (APO).☆54Updated last year
- Self-Alignment with Principle-Following Reward Models☆161Updated 3 weeks ago
- ☆85Updated last year
- A repository for transformer critique learning and generation☆89Updated last year
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆28Updated last year
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆46Updated last year
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆29Updated last year
- ☆48Updated 3 weeks ago
- ☆159Updated 2 years ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆44Updated last month
- Self-Supervised Alignment with Mutual Information☆18Updated last year
- Online Adaptation of Language Models with a Memory of Amortized Contexts (NeurIPS 2024)☆63Updated 10 months ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆159Updated last week
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆55Updated 3 months ago
- ☆28Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆47Updated last year
- ☆40Updated last year
- This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DP…☆25Updated 5 months ago
- Code accompanying the paper Pretraining Language Models with Human Preferences☆182Updated last year
- ☆45Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆75Updated 9 months ago